Sagemake model package creation ValidationException around supported instance

0

Hi community,

I'm using Python boto/sagemaker SDK to create Sagemaker model packages, it was mostly fine but I run into issue when using ml.g5 family as supported instance types:

ClientError: An error occurred (ValidationException) when calling the CreateModelPackage operation: 1 validation error detected: Value '[ml.p2.xlarge, ml.p2.8xlarge, ml.p2.16xlarge, ml.p3.2xlarge, ml.p3.8xlarge, ml.p3.16xlarge, ml.g4dn.xlarge, ml.g4dn.2xlarge, ml.g4dn.4xlarge, ml.g4dn.8xlarge, ml.g4dn.12xlarge, ml.g4dn.16xlarge, ml.g5.xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.g5.12xlarge, ml.g5.16xlarge, ml.g5.24xlarge, ml.g5.48xlarge]' at 'inferenceSpecification.supportedTransformInstanceTypes' failed to satisfy constraint: Member must satisfy constraint: [Member must satisfy enum value set: [ml.m5.4xlarge, ml.p2.xlarge, ml.m4.16xlarge, ml.m5.large, ml.p3.16xlarge, ml.p2.16xlarge, ml.c4.2xlarge, ml.c5.2xlarge, ml.c4.4xlarge, ml.c5.4xlarge, ml.g4dn.xlarge, ml.g4dn.12xlarge, ml.g4dn.2xlarge, ml.c4.8xlarge, ml.g4dn.4xlarge, ml.c5.9xlarge, ml.g4dn.16xlarge, ml.c5.xlarge, ml.c4.xlarge, ml.g4dn.8xlarge, ml.c5.18xlarge, ml.p3.2xlarge, ml.m5.xlarge, ml.m4.10xlarge, ml.m5.12xlarge, ml.m4.xlarge, ml.m5.24xlarge, ml.m4.2xlarge, ml.m5.2xlarge, ml.p2.8xlarge, ml.p3.8xlarge, ml.m4.4xlarge]]

I don't have such problem when using p2, p3 and g4dn though, so I'm wondering where is such restriction posted from? My account? region?

Thanks!

Zac
asked 6 months ago121 views
1 Answer
0
Accepted Answer

This can be closed now, turned out batch transform didn't like g5 according to

https://docs.aws.amazon.com/cli/latest/reference/sagemaker/create-model-package.html

Zac
answered 6 months ago

You are not logged in. Log in to post an answer.

A good answer clearly answers the question and provides constructive feedback and encourages professional growth in the question asker.

Guidelines for Answering Questions